Computer-Aided Diagnosis of Different Rotator Cuff Lesions Using Shoulder Musculoskeletal Ultrasound

Ruey Feng Chang, Chung Chien Lee, Chung Ming Lo

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The lifetime prevalence of shoulder pain approaches 70%, which is mostly attributable to rotator cuff lesions such as inflammation, calcific tendinitis and tears. On clinical examination, shoulder ultrasound is recommended for the detection of lesions. However, there exists inter-operator variability in diagnostic accuracy because of differences in the experience and expertise of operators. In this study, a computer-aided diagnosis (CAD) system was developed to assist ultrasound operators in diagnosing rotator cuff lesions and to improve the practicality of ultrasound examination. The collected cases included 43 cases of inflammation, 30 cases of calcific tendinitis and 26 tears. For each case, the lesion area and texture features were extracted from the entire lesions and combined in a multinomial logistic regression classifier for lesion classification. The proposed CAD achieved an accuracy of 87.9%. The individual accuracy of this CAD system was 88.4% for inflammation, 83.3% for calcific tendinitis and 92.3% for tears. Cohen's k was 0.798. On the basis of its diagnostic performance, clinical use of this CAD technique has promise.

Original languageEnglish
Pages (from-to)2315-2322
Number of pages8
JournalUltrasound in Medicine and Biology
Volume42
Issue number9
DOIs
Publication statusPublished - Sep 1 2016

Fingerprint

cuffs
Rotator Cuff
shoulders
lesions
Tendinopathy
Inflammation
Tears
operators
Shoulder Pain
examination
pain
Logistic Models
logistics
classifiers
regression analysis
textures
life (durability)

Keywords

  • Computer-aided diagnosis
  • Rotator cuff lesions
  • Shoulder ultrasound
  • Texture

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

Computer-Aided Diagnosis of Different Rotator Cuff Lesions Using Shoulder Musculoskeletal Ultrasound. / Chang, Ruey Feng; Lee, Chung Chien; Lo, Chung Ming.

In: Ultrasound in Medicine and Biology, Vol. 42, No. 9, 01.09.2016, p. 2315-2322.

Research output: Contribution to journalArticle

Chang, Ruey Feng ; Lee, Chung Chien ; Lo, Chung Ming. / Computer-Aided Diagnosis of Different Rotator Cuff Lesions Using Shoulder Musculoskeletal Ultrasound. In: Ultrasound in Medicine and Biology. 2016 ; Vol. 42, No. 9. pp. 2315-2322.
@article{aa79adc93cc74a04ac28e99e5915e4bb,
title = "Computer-Aided Diagnosis of Different Rotator Cuff Lesions Using Shoulder Musculoskeletal Ultrasound",
abstract = "The lifetime prevalence of shoulder pain approaches 70{\%}, which is mostly attributable to rotator cuff lesions such as inflammation, calcific tendinitis and tears. On clinical examination, shoulder ultrasound is recommended for the detection of lesions. However, there exists inter-operator variability in diagnostic accuracy because of differences in the experience and expertise of operators. In this study, a computer-aided diagnosis (CAD) system was developed to assist ultrasound operators in diagnosing rotator cuff lesions and to improve the practicality of ultrasound examination. The collected cases included 43 cases of inflammation, 30 cases of calcific tendinitis and 26 tears. For each case, the lesion area and texture features were extracted from the entire lesions and combined in a multinomial logistic regression classifier for lesion classification. The proposed CAD achieved an accuracy of 87.9{\%}. The individual accuracy of this CAD system was 88.4{\%} for inflammation, 83.3{\%} for calcific tendinitis and 92.3{\%} for tears. Cohen's k was 0.798. On the basis of its diagnostic performance, clinical use of this CAD technique has promise.",
keywords = "Computer-aided diagnosis, Rotator cuff lesions, Shoulder ultrasound, Texture",
author = "Chang, {Ruey Feng} and Lee, {Chung Chien} and Lo, {Chung Ming}",
year = "2016",
month = "9",
day = "1",
doi = "10.1016/j.ultrasmedbio.2016.05.016",
language = "English",
volume = "42",
pages = "2315--2322",
journal = "Ultrasound in Medicine and Biology",
issn = "0301-5629",
publisher = "Elsevier USA",
number = "9",

}

TY - JOUR

T1 - Computer-Aided Diagnosis of Different Rotator Cuff Lesions Using Shoulder Musculoskeletal Ultrasound

AU - Chang, Ruey Feng

AU - Lee, Chung Chien

AU - Lo, Chung Ming

PY - 2016/9/1

Y1 - 2016/9/1

N2 - The lifetime prevalence of shoulder pain approaches 70%, which is mostly attributable to rotator cuff lesions such as inflammation, calcific tendinitis and tears. On clinical examination, shoulder ultrasound is recommended for the detection of lesions. However, there exists inter-operator variability in diagnostic accuracy because of differences in the experience and expertise of operators. In this study, a computer-aided diagnosis (CAD) system was developed to assist ultrasound operators in diagnosing rotator cuff lesions and to improve the practicality of ultrasound examination. The collected cases included 43 cases of inflammation, 30 cases of calcific tendinitis and 26 tears. For each case, the lesion area and texture features were extracted from the entire lesions and combined in a multinomial logistic regression classifier for lesion classification. The proposed CAD achieved an accuracy of 87.9%. The individual accuracy of this CAD system was 88.4% for inflammation, 83.3% for calcific tendinitis and 92.3% for tears. Cohen's k was 0.798. On the basis of its diagnostic performance, clinical use of this CAD technique has promise.

AB - The lifetime prevalence of shoulder pain approaches 70%, which is mostly attributable to rotator cuff lesions such as inflammation, calcific tendinitis and tears. On clinical examination, shoulder ultrasound is recommended for the detection of lesions. However, there exists inter-operator variability in diagnostic accuracy because of differences in the experience and expertise of operators. In this study, a computer-aided diagnosis (CAD) system was developed to assist ultrasound operators in diagnosing rotator cuff lesions and to improve the practicality of ultrasound examination. The collected cases included 43 cases of inflammation, 30 cases of calcific tendinitis and 26 tears. For each case, the lesion area and texture features were extracted from the entire lesions and combined in a multinomial logistic regression classifier for lesion classification. The proposed CAD achieved an accuracy of 87.9%. The individual accuracy of this CAD system was 88.4% for inflammation, 83.3% for calcific tendinitis and 92.3% for tears. Cohen's k was 0.798. On the basis of its diagnostic performance, clinical use of this CAD technique has promise.

KW - Computer-aided diagnosis

KW - Rotator cuff lesions

KW - Shoulder ultrasound

KW - Texture

UR - http://www.scopus.com/inward/record.url?scp=84991200839&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84991200839&partnerID=8YFLogxK

U2 - 10.1016/j.ultrasmedbio.2016.05.016

DO - 10.1016/j.ultrasmedbio.2016.05.016

M3 - Article

C2 - 27381057

AN - SCOPUS:84991200839

VL - 42

SP - 2315

EP - 2322

JO - Ultrasound in Medicine and Biology

JF - Ultrasound in Medicine and Biology

SN - 0301-5629

IS - 9

ER -